Struct SubsetDataset 

pub struct SubsetDataset<D>
where
    D: Dataset,
{
    pub wrapped: Arc<D>,
    pub indices: Vec<usize>,
}

Fields

wrapped: Arc<D>

indices: Vec<usize>

Implementations

impl<D: Dataset> SubsetDataset<D>

pub fn new(dataset: impl Into<Arc<D>>, indices: Vec<usize>) -> Self

Creates a new selection dataset with the given dataset and indices without checking bounds.

Arguments

• dataset - The original dataset to select from.
• indices - A vector of indices to select from the dataset.

pub fn from_indices( dataset: impl Into<Arc<D>>, indices: Vec<usize>, ) -> SubsetDatasetResult<Self>

Creates a new selection dataset with the given dataset and indices.

Checks that all indices are within the bounds of the dataset.

Arguments

• dataset - The original dataset to select from.
• indices - A slice of indices to select from the dataset. These indices must be within the bounds of the dataset.

pub fn select_all(dataset: impl Into<Arc<D>>) -> Self

Creates a new selection dataset that selects all indices from the dataset.

This allocates a 1-to-1 mapping of indices to the dataset size, essentially functioning as a no-op selection. This is only useful when the dataset will later be shuffled or transformed in place.

Arguments

• dataset - The original dataset to select from.

Returns

A new SubsetDataset that selects all indices from the dataset.

pub fn slice(&self, start: usize, end: usize) -> SubsetDatasetResult<Self>

Creates a new dataset that is a slice of the current selection dataset.

Slices the selection indices from [start..end].

Independent of future shuffles on the parent, but shares the same wrapped dataset.

Arguments

• start - The start of the range.
• end - The end of the range (exclusive).

pub fn split(&self, num: usize) -> SubsetDatasetResult<Vec<Self>>

Split into num datasets by slicing the selection indices evenly.

Split is done via slice, so the datasets share the same wrapped dataset.

Independent of future shuffles on the parent, but shares the same wrapped dataset.

Arguments

• num - The number of datasets to split into.

Returns

A vector of SubsetDataset instances, each containing a subset of the indices.

Trait Implementations

impl<D: Dataset> Dataset for SubsetDataset<D>

type Item = <D as Dataset>::Item

type Error = <D as Dataset>::Error

fn get(&self, index: usize) -> Result<Option<Self::Item>, Self::Error>

Gets the item at the given index.

fn len(&self) -> usize

Gets the number of items in the dataset.

fn is_empty(&self) -> bool

Checks if the dataset is empty.

fn iter(&self) -> DatasetIterator<'_, Self>

where Self: Sized,

Returns an iterator over the dataset.